Now available: SD1.5 version
Tired of SD producing overblown, bright images?
This LORA model is trained using the technique described in https://www.crosslabs.org//blog/diffusion-with-offset-noise
Use it to produce beautiful, high-contrast, low-key images that SD just wasn't capable of creating until now.
Sample images were generated using Illuminati Diffusion v1.0
The LORA was trained using Kohya's LORA Dreambooth script, on SD2.1-768 and SD1.5 with a dataset of 44 low-key, high-quality, high-contrast photographs.
Seeing is believing: On the left is an image without the LORA, on the right is with the LORA.